Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9af9d31c632db36d0a55bbdaafbffc987b00d39f9bac76b408821aae721a2a8a
+oid sha256:8c890dac25841ad3328e4fb3a782daa8b803618fb11cc4c2528f21764ee15775
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc7f363b3db8e609b38da8c5306c4320bae0f7c809ef09d4ae7147be47705ec8
+oid sha256:afb060ee2cac02dd5c62f787910a843ab46452e74449e698ba22f15f76e8c9a2
 size 205350

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ea8f278f29641100a56e280ef65934b0fccc8f8d9851be121c701ebed8ce795
+oid sha256:755c4134596a2077827fb8f97d56f3bd342fd2c77507989a663da481d9802231
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00995850622406639,
+  "epoch": 0.01991701244813278,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 189.966,
       "eval_steps_per_second": 47.492,
       "step": 3
+    },
+    {
+      "epoch": 0.013278008298755186,
+      "grad_norm": 0.11774402111768723,
+      "learning_rate": 8e-05,
+      "loss": 10.3769,
+      "step": 4
+    },
+    {
+      "epoch": 0.016597510373443983,
+      "grad_norm": 0.12266664206981659,
+      "learning_rate": 0.0001,
+      "loss": 10.3728,
+      "step": 5
+    },
+    {
+      "epoch": 0.01991701244813278,
+      "grad_norm": 0.11839405447244644,
+      "learning_rate": 0.00012,
+      "loss": 10.3754,
+      "step": 6
+    },
+    {
+      "epoch": 0.01991701244813278,
+      "eval_loss": 10.374419212341309,
+      "eval_runtime": 2.8668,
+      "eval_samples_per_second": 177.202,
+      "eval_steps_per_second": 44.301,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 748441042944.0,
+  "total_flos": 1496882085888.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null